mlsanityData to 14 Oct 2026

Improving 3D Pose Estimation for Sign Language

arXiv 2308.09525 ↗First posted 18 Aug 2023cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

This work addresses 3D human pose reconstruction in single images. We present a method that combines Forward Kinematics (FK) with neural networks to ensure a fast and valid prediction of 3D pose. Pose is represented as a hierarchical tree/graph with nodes corresponding to human joints that model their physical limits. Given a 2D detection of keypoints in the image, we lift the skeleton to 3D using neural networks to predict both the joint rotations and bone lengths. These predictions are then combined with skeletal constraints using an FK layer implemented as a network layer in PyTorch. The result is a fast and accurate approach to the estimation of 3D skeletal pose. Through quantitative and qualitative evaluation, we demonstrate the method is significantly more accurate than MediaPipe in terms of both per joint positional error and visual appearance. Furthermore, we demonstrate generalization over different datasets. The implementation in PyTorch runs at between 100-200 milliseconds per image (including CNN detection) using CPU only.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 21 of its 37 references that are in the map. First posted on arXiv 18 Aug 2023.

Builds on

21 of 37 references.

References · 21

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  3. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  4. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  5. 2019MediaPipe: A Framework for Building Perception Pipelinescited by 583
  6. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
  7. 2017Geometric Loss Functions for Camera Pose Regression with Deep Learningcited by 224
  8. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  9. 2016Panoptic Studio: A Massively Multiview System for Social Interaction Capturecited by 173
  10. 2018Monocular Total Capture: Posing Face, Body, and Hands in the Wildcited by 162
  11. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 142
  12. 2018QuaterNet: A Quaternion-based Recurrent Model for Human Motioncited by 109
9 more
  1. 2020BSL-1K: Scaling up co-articulated sign language recognition using mouthing cuescited by 106
  2. 2018Neural Kinematic Networks for Unsupervised Motion Retargettingcited by 88
  3. 2020An Analysis of SVD for Deep Rotation Estimationcited by 86
  4. 2017Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Imagecited by 73
  5. 2021ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Posescited by 35
  6. 2021BBC-Oxford British Sign Language Datasetcited by 28
  7. 2016A Simple, Fast and Highly-Accurate Algorithm to Recover 3D Shape from 2D Landmarks on a Single Imagecited by 8
  8. 2019Weakly-Supervised 3D Pose Estimation from a Single Image using Multi-View Consistencycited by 8
  9. 20213D Pose Estimation and Future Motion Prediction from 2D Imagescited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 8; 2026: 3.

16 papers.

Sort:

  1. 2024A Data-Driven Representation for Sign Language Productioncited by 17
  2. 2025SignRep: Enhancing Self-Supervised Sign Representationscited by 15
  3. 2025Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translationcited by 12
  4. 2025Hands-On: Segmenting Individual Signs from Continuous Sequencescited by 10
  5. 2024Sign Stitching: A Novel Approach to Sign Language Productioncited by 8
  6. 2025Meaningful Pose-Based Sign Language Evaluationcited by 6
  7. 2025Disentangle and Regularize: Sign Language Production with Articulator-Based Disentanglement and Channel-Aware Regularizationcited by 5
  8. 2025SLRTP2025 Sign Language Production Challenge: Methodology, Results, and Future Workcited by 4
  9. 2024Modelling the Distribution of Human Motion for Sign Language Assessmentcited by 3
  10. 2025Using Sign Language Production as Data Augmentation to enhance Sign Language Translationcited by 3
  11. 2026SignSparK: Efficient Multilingual Sign Language Production via Sparse Keyframe Learningcited by 2
  12. 2024Two Hands Are Better Than One: Resolving Hand to Hand Intersections via Occupancy Networkscited by 1
4 more
  1. 2024PAFUSE: Part-based Diffusion for 3D Whole-Body Pose Estimationcited by 1
  2. 2025SAGE: Segment-Aware Gloss-Free Encoding for Token-Efficient Sign Language Translationcited by 1
  3. 2026A2V-SLP: Alignment-Aware Variational Modeling for Disentangled Sign Language Productioncited by 0
  4. 2026SignRR: Retrieve and Refine Real Motion for Sign Language Productioncited by 0